© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14255
    Prev
    Next
    INDEX
    Explanations

    non-english words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "
    -1.52
    }
    -1.46
    不久
    -1.45
    Escrito
    -1.43
    Of
    -1.43
    s
    -1.42
    '
    -1.41
     черво
    -1.39
    Entrevista
    -1.38
     proveniente
    -1.38
    POSITIVE LOGITS
     in
    1.61
    ⛦
    1.58
     princesas
    1.49
    部の
    1.48
    aed
    1.48
    ING
    1.47
     sehat
    1.46
     Yankee
    1.42
     رائعة
    1.42
     جيدة
    1.41
    Activations Density 0.108%

    No Known Activations